From the course: Deep Learning: Getting Started
Join today to access over 24,900 courses taught by industry experts.
Predictions with deep learning models
From the course: Deep Learning: Getting Started
Predictions with deep learning models
- [Tutor] Having trained a deep learning model for Iris, let's do some predictions with new data. We start with a prediction input of four feature variables namely; sepal length, sepal width, petal length and Petal width. The featured variables need to go through the same set of pre-processing that was done during training. We use the same scaler model we built during training to scale the prediction feature variables too. Then we use the predict method on the model to predict for the scale input. The raw prediction results are captured and printed. The result is a list of probabilities of the various classes, asset applies for this input. We then use the argmax function to get the index of the highest probability. Then we use the same training label encoder to do the reverse transform and get the string for the species name. Let's run this code and review the results. For the raw output, we see the probabilities for the three classes namely; setosa, versicolor and virginica. The sum…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.